import xarray as xr
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

from sklearn.model_selection import train_test_split
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.compose import TransformedTargetRegressor

from sklearn.ensemble import ExtraTreesRegressor
from sklearn.ensemble import BaggingRegressor

from sklearn.metrics import root_mean_squared_error as rmse

from tqdm import tqdm

import dill
import random

import salishsea_tools.viz_tools as sa_vi

def datasets_preparation(dataset, dataset2):
    
    drivers = np.stack([np.ravel(dataset['Temperature_(0m-15m)']),
        np.ravel(dataset['Temperature_(15m-100m)']), 
        np.ravel(dataset['Salinity_(0m-15m)']),
        np.ravel(dataset['Salinity_(15m-100m)']),
        np.ravel(dataset2['Summation_of_solar_radiation']),
        np.ravel(dataset2['Mean_wind_speed'])
        ])
    indx = np.where(~np.isnan(drivers).any(axis=0))
    drivers = drivers[:,indx[0]]

    diat = np.ravel(dataset['Diatom'])
    diat = diat[indx[0]]

    return(drivers, diat, indx)

def regressor (inputs, targets):
    
    inputs = inputs.transpose()
    
    # Regressor
    X_train, _, y_train, _ = train_test_split(inputs, targets, train_size=0.35)

    model = ExtraTreesRegressor()
    model = make_pipeline(StandardScaler(), model)
    regr = BaggingRegressor(model, n_estimators=12, n_jobs=4).fit(X_train, y_train)

    return (regr)

def regressor2 (inputs, targets, variable_name):

    inputs2 = inputs.transpose()

    outputs_test = regr.predict(inputs2)
   
    m = scatter_plot(targets, outputs_test, variable_name) 
    r = np.round(np.corrcoef(targets, outputs_test)[0][1],3)
    rms = rmse(targets, outputs_test)

    return (r, rms, m)

def regressor3 (inputs, targets):
  
    inputs2 = inputs.transpose()

    outputs_test = regr.predict(inputs2)
   
    # compute slope m and intercept b
    m, b = np.polyfit(targets, outputs_test, deg=1)
    
    r = np.round(np.corrcoef(targets, outputs_test)[0][1],3)
    rms = rmse(targets, outputs_test)

    return (r, rms, m)

def regressor4 (inputs, targets, variable_name):

    inputs2 = inputs.transpose()
    
    outputs = regr.predict(inputs2)

    # Post processing
    indx2 = np.full((len(diat_i.y)*len(diat_i.x)),np.nan)
    indx2[indx[0]] = outputs
    model = np.reshape(indx2,(len(diat_i.y),len(diat_i.x)))

    m = scatter_plot(targets, outputs, variable_name + str(dates[i].date())) 

    # Preparation of the dataarray 
    model = xr.DataArray(model,
        coords = {'y': diat_i.y, 'x': diat_i.x},
        dims = ['y','x'],
        attrs=dict( long_name = variable_name + "Concentration",
        units="mmol m-2"),)
                        
    plotting3(targets, model, diat_i, variable_name)

def printing (targets, outputs, m):

    print ('The amount of data points is', outputs.size)
    print ('The slope of the best fitting line is ', np.round(m,3))
    print ('The correlation coefficient is:', np.round(np.corrcoef(targets, outputs)[0][1],3))
    print (' The mean square error is:', rmse(targets,outputs))

def scatter_plot(targets, outputs, variable_name):

    # compute slope m and intercept b
    m, b = np.polyfit(targets, outputs, deg=1)

    printing(targets, outputs, m)

    fig, ax = plt.subplots(2, figsize=(5,10), layout='constrained')

    ax[0].scatter(targets,outputs, alpha = 0.2, s = 10)

    lims = [np.min([ax[0].get_xlim(), ax[0].get_ylim()]),
        np.max([ax[0].get_xlim(), ax[0].get_ylim()])]

    # plot fitted y = m*x + b
    ax[0].axline(xy1=(0, b), slope=m, color='r')

    ax[0].set_xlabel('targets')
    ax[0].set_ylabel('outputs')
    ax[0].set_xlim(lims)
    ax[0].set_ylim(lims)
    ax[0].set_aspect('equal')

    ax[0].plot(lims, lims,linestyle = '--',color = 'k')

    h = ax[1].hist2d(targets,outputs, bins=100, cmap='jet', 
        range=[lims,lims], cmin=0.1, norm='log')
    
    ax[1].plot(lims, lims,linestyle = '--',color = 'k')

    # plot fitted y = m*x + b
    ax[1].axline(xy1=(0, b), slope=m, color='r')

    ax[1].set_xlabel('targets')
    ax[1].set_ylabel('outputs')
    ax[1].set_aspect('equal')

    fig.colorbar(h[3],ax=ax[1], location='bottom')

    fig.suptitle(variable_name)

    plt.show()

    return (m)

def plotting(variable, name):

    plt.plot(years,variable, marker = '.', linestyle = '')
    plt.xlabel('Years')
    plt.ylabel(name)
    plt.show()

def plotting2(variable,title):
    
    fig, ax = plt.subplots()

    scatter= ax.scatter(dates,variable, marker='.', c=pd.DatetimeIndex(dates).month)

    ax.legend(handles=scatter.legend_elements()[0], labels=['February','March','April'])
    fig.suptitle('Daily ' + title + ' (15 Feb - 30 Apr)')
    
    fig.show()

def plotting3(targets, model, variable, variable_name):

    fig, ax = plt.subplots(2,2, figsize = (10,15))

    cmap = plt.get_cmap('cubehelix')
    cmap.set_bad('gray')

    variable.plot(ax=ax[0,0], cmap=cmap, vmin = targets.min(), vmax =targets.max(), cbar_kwargs={'label': variable_name + ' Concentration  [mmol m-2]'})
    model.plot(ax=ax[0,1], cmap=cmap, vmin = targets.min(), vmax = targets.max(), cbar_kwargs={'label': variable_name + ' Concentration  [mmol m-2]'})
    ((variable-model) / variable * 100).plot(ax=ax[1,0], cmap=cmap, cbar_kwargs={'label': variable_name + ' Concentration  [percentage]'})

    plt.subplots_adjust(left=0.1,
        bottom=0.1, 
        right=0.95, 
        top=0.95, 
        wspace=0.35, 
        hspace=0.35)

    sa_vi.set_aspect(ax[0,0])
    sa_vi.set_aspect(ax[0,1])
    sa_vi.set_aspect(ax[1,0])


    ax[0,0].title.set_text(variable_name + ' (targets)')
    ax[0,1].title.set_text(variable_name + ' (outputs)')
    ax[1,0].title.set_text('targets - outputs')
    ax[1,1].axis('off')

    fig.suptitle(str(dates[i].date()))

    plt.show()

ds = xr.open_dataset('/data/ibougoudis/MOAD/files/integrated_model_var_old.nc')
ds2 = xr.open_dataset('/data/ibougoudis/MOAD/files/external_inputs.nc')

ds = ds.isel(time_counter = (np.arange(0, len(ds.time_counter),2)), 
    y=(np.arange(ds.y[0], ds.y[-1], 5)), 
    x=(np.arange(ds.x[0], ds.x[-1], 5)))

ds2 = ds2.isel(time_counter = (np.arange(0, len(ds2.time_counter),2)), 
    y=(np.arange(ds2.y[0], ds2.y[-1], 5)), 
    x=(np.arange(ds2.x[0], ds2.x[-1], 5)))

dates = pd.DatetimeIndex(ds['time_counter'].values)

drivers, diat, _ = datasets_preparation(ds, ds2)

regr = regressor(drivers, diat)

years = range (2007,2024)

r_all = []
rms_all = []
slope_all = []

for year in tqdm(range (2007,2024)):
    
    dataset = ds.sel(time_counter=str(year))
    dataset2 = ds2.sel(time_counter=str(year))
    
    drivers, diat, _ = datasets_preparation(dataset, dataset2)

    r, rms, m = regressor2(drivers, diat, 'Diatom ' + str(year))
    
    r_all.append(r)
    rms_all.append(rms)
    slope_all.append(m)
    
plotting(np.transpose(r_all), 'Correlation Coefficient')
plotting(np.transpose(rms_all), 'Root Mean Square Error')
plotting (np.transpose(slope_all), 'Slope of the best fitting line')

  0%|          | 0/17 [00:00<?, ?it/s]

The amount of data points is 70794
The slope of the best fitting line is  0.738
The correlation coefficient is: 0.918
 The mean square error is: 0.06581317458970341

  6%|▌         | 1/17 [01:16<20:22, 76.39s/it]

The amount of data points is 70794
The slope of the best fitting line is  0.729
The correlation coefficient is: 0.883
 The mean square error is: 0.06867923153926321

 12%|█▏        | 2/17 [02:27<18:16, 73.09s/it]

The amount of data points is 68931
The slope of the best fitting line is  0.756
The correlation coefficient is: 0.927
 The mean square error is: 0.07751808111193076

 18%|█▊        | 3/17 [03:36<16:38, 71.35s/it]

The amount of data points is 70794
The slope of the best fitting line is  0.726
The correlation coefficient is: 0.915
 The mean square error is: 0.0619161166591015

 24%|██▎       | 4/17 [04:43<15:04, 69.54s/it]

The amount of data points is 68931
The slope of the best fitting line is  0.806
The correlation coefficient is: 0.932
 The mean square error is: 0.05813325524217016

r_all2 = np.array([])
rms_all2 = np.array([])
slope_all2 = np.array([])

for i in tqdm(range (0, len(ds.time_counter))):
    
    dataset = ds.isel(time_counter=i)
    dataset2 = ds2.isel(time_counter=i)

    drivers, diat, _ = datasets_preparation(dataset, dataset2)

    r, rms, m = regressor3(drivers, diat)

    r_all2 = np.append(r_all2,r)
    rms_all2 = np.append(rms_all2,rms)
    slope_all2 = np.append(slope_all2,m)

plotting2(r_all2, 'Correlation Coefficients')
plotting2(rms_all2, 'Root Mean Square Errors')
plotting2(slope_all2, 'Slope of the best fitting line')

100%|██████████| 640/640 [11:11:27<00:00, 62.95s/it]

maps = random.sample(range(0,len(ds.time_counter)),10)

for i in tqdm(maps):

    dataset = ds.isel(time_counter=i)
    dataset2 = ds2.isel(time_counter=i)
    drivers, diat, indx = datasets_preparation(dataset, dataset2)

    diat_i = dataset['Diatom']

    regressor4(drivers, diat, 'Diatom ')

  0%|          | 0/10 [00:00<?, ?it/s]

The amount of data points is 1863
The slope of the best fitting line is  0.647
The correlation coefficient is: 0.897
 The mean square error is: 0.10480773003649026

 10%|█         | 1/10 [01:05<09:52, 65.80s/it]

The amount of data points is 1863
The slope of the best fitting line is  0.606
The correlation coefficient is: 0.773
 The mean square error is: 0.06227340657842682

 20%|██        | 2/10 [02:11<08:45, 65.70s/it]

The amount of data points is 1863
The slope of the best fitting line is  0.963
The correlation coefficient is: 0.853
 The mean square error is: 0.03875772320600051

 30%|███       | 3/10 [03:18<07:43, 66.24s/it]

The amount of data points is 1863
The slope of the best fitting line is  0.451
The correlation coefficient is: 0.548
 The mean square error is: 0.10725482913764549

 40%|████      | 4/10 [04:27<06:43, 67.32s/it]

The amount of data points is 1863
The slope of the best fitting line is  0.595
The correlation coefficient is: 0.854
 The mean square error is: 0.07082650334617817

Script to reproduce years based on a model trained with random points¶

Importing¶

Datasets Preparation¶

Regressor¶

Regressor 2¶

Regressor 3¶

Regressor 4¶

Printing¶

Scatter Plot¶

Plotting¶

Plotting 2¶

Plotting 3¶

Training (Random Points)¶

Other Years (Anually)¶

Other Years (Daily)¶

Daily Maps¶